@article{mash-etal-2026-paraclean,
    title = "{P}ara{CLEAN}: Improving Translation Quality through Systematic Parallel Data Cleaning",
    author = "Mash, Audrey  and
      Bohman, Ella Paulina  and
      Melero, Maite",
    editor = "Piperidis, Stelios  and
      Bel, N{\'u}ria  and
      van den Heuvel, Henk  and
      Ide, Nancy  and
      Krek, Simon  and
      Toral, Antonio",
    journal = "International Conference on Language Resources and Evaluation",
    volume = "main",
    month = may,
    year = "2026",
    address = "Palma de Mallorca, Spain",
    publisher = "ELRA Language Resource Association",
    url = "https://preview.aclanthology.org/ingest-lrec/2026.lrec-main.527/",
    pages = "6630--6640",
    abstract = "Parallel corpora often contain significant noise, particularly in low-resource settings where both collected and synthetic data are combined. We present ParaCLEAN, a modular pipeline for cleaning parallel data that integrates embeddings-based filtering, language identification, deduplication, and normalisation. Experiments on Catalan to Japanese translation demonstrate that ParaCLEAN improves data quality and downstream MT performance. Ablation studies highlight the contribution of each step. ParaCLEAN is lightweight, reproducible, and extensible for diverse language pairs."
}